List of Datasets

UGV

Rawseeds

SLAM

Indoor and outdoor ground-robot SLAM dataset with RGB, fisheye, trinocular, lidar, RTK, and tag or laser ground truth.

Metadata: Complete Metadata source documented Released 2009

Primary places to inspect, download, read about, or reproduce the dataset.

Download

Not reported

Code

Not reported

Quick facts

Vehicle type
UGV
Environment
Indoor, Outdoor
Data origin
Real-world
Sensor count
12
Ground truth
Available
Calibration
Parameters Only
Annotations
Not reported

Sensor overview

High-level sensor availability before the detailed sensor records below.

Cameras

5 reported

IMUs

1 reported

GNSS

1 reported

LiDAR

4 reported

Magnetometers

Not reported

Barometers

Not reported

UWB

Not reported

Ground truth

Reference scope, method, rate, coverage, and provenance.

Scope Method Reference system Count Rate Coverage Reference provenance
External
Measured using equipment independent of the platform’s normal onboard sensor pipeline.
Derived
Computed primarily from the dataset’s own recorded sensors.
Hybrid
Combines independent reference equipment with onboard measurements.
3D position RTK GNSS Not reported Not reported 5 Hz Full Reference provenance
External
Measured using equipment independent of the platform’s normal onboard sensor pipeline.
Derived
Computed primarily from the dataset’s own recorded sensors.
Hybrid
Combines independent reference equipment with onboard measurements.
External
Accuracy and notes
Accuracy notes
Reported RTK GPS precision is 2–6 cm.
Reference notes
Outdoor position ground truth from RTK GPS.
2D + heading Surveyed markers Not reported Not reported Not reported Partial · Indoor Subsets Reference provenance
External
Measured using equipment independent of the platform’s normal onboard sensor pipeline.
Derived
Computed primarily from the dataset’s own recorded sensors.
Hybrid
Combines independent reference equipment with onboard measurements.
External
Accuracy and notes
Accuracy notes
Visual-marker tracking can exhibit larger pose-error peaks than laser tracking.
Reference notes
Independent fixed-camera marker tracking. Basler Scout scA640 cameras belong to this external reference network rather than the onboard sensor suite.
2D + heading Other Not reported Not reported Not reported Partial · Indoor Subsets Reference provenance
External
Measured using equipment independent of the platform’s normal onboard sensor pipeline.
Derived
Computed primarily from the dataset’s own recorded sensors.
Hybrid
Combines independent reference equipment with onboard measurements.
External
Accuracy and notes
Reference notes
Independent fixed-laser tracking requires a visible, well-defined robot profile and can be affected by occlusion in cluttered spaces.

Calibration and synchronization

Reported calibration level, reproducibility signals, and supporting notes.

Level
Parameters Only
Processed parameters
Available
Raw calibration data
Not reported
Calibration targets
Not reported

Parameters only

Processed calibration parameters are reported, but raw calibration data is not reported.

Notes

Onboard sensor calibration and the intrinsic/extrinsic calibration of the external ground-truth camera and laser networks are documented; raw calibration sequences are not established by the reviewed source.

Known or intentional limitations

Reported constraints and characteristics to check before using the dataset.

Indoor ground truth covers only subsets of the explored areas and varies by location and reference-system visibility.

Visual-marker ground truth requires reasonably uniform illumination and can exhibit larger pose-error peaks than laser ground truth.

Laser ground truth estimates planar 3DoF pose and requires a visible, well-defined robot profile; occlusion in cluttered spaces can favor the camera system.

Cameras

mono-rgb

Model
Unibrain Fire-i 400
Setup
Mono
Count
1
Effective cameras
1
Modality
Rgb
Resolution
640 x 480
Rate
30 Hz
Shutter
Not Reported
Lens type
Not Reported
HFOV
Not reported
VFOV
Not reported

omnidirectional-rgb

Model
Prosilica GC1020C with Vstone hyperbolic mirror
Setup
Omnidirectional
Count
1
Effective cameras
1
Modality
Rgb
Resolution
640 x 640
Rate
15 Hz
Shutter
Not Reported
Lens type
Not Reported
HFOV
Not reported
VFOV
Not reported

trinocular-gray

Model
Videre Design STH-DCSG-VAR with additional DCSG camera
Setup
Trinocular
Count
1
Effective cameras
3
Modality
Grayscale
Resolution
640 x 480
Rate
15 Hz
Shutter
Not Reported
Lens type
Not Reported
HFOV
Not reported
VFOV
Not reported

IMUs

Xsens MTi

Model
Xsens MTi
Count
1
Accel / gyro
128 / 128 Hz

GNSS

RTK GPS

Model or name
RTK GPS
Count
1
Rate
5 Hz
GNSS type
RTK
Position output
Available
Velocity output
Not reported
Heading output
Not reported

LiDAR

Hokuyo URG-04LX

Model or name
Hokuyo URG-04LX
Count
2
Dimensions
2
Rate
10 Hz
Channels
Not reported
Range
Not reported

SICK LMS291

Model or name
SICK LMS291
Count
1
Dimensions
2
Rate
75 Hz
Channels
Not reported
Range
Not reported

SICK LMS200

Model or name
SICK LMS200
Count
1
Dimensions
2
Rate
75 Hz
Channels
Not reported
Range
Not reported

Additional sensors

Odometry

Name
Robocom base odometry
Count
1

Other sensor

Model
Maxbotix EZ-2
Name
Sonar belt
Variation
Ultrasonic range sensor
Count
12
Coverage
indoor datasets

Annotations

Reported annotation availability and task support.

Availability
Not reported
Format
Not reported
Class count
Not reported
Semantic segmentation Not reported
Instance segmentation Not reported
Object detection Not reported
Optical flow Not reported
Depth ground truth Not reported

Citation

Citation key and BibTeX kept at the end of the page for reference.

Citation key
Ceriani2009

BibTeX

@article{Ceriani2009,
  title = {Rawseeds Ground Truth Collection Systems for Indoor Self-Localization and Mapping},
  author = {Ceriani, Simone and Fontana, Giulio and Giusti, Alessandro and Marzorati, Daniele and Matteucci, Matteo and Migliore, Davide and Rizzi, Davide and Sorrenti, Domenico G. and Taddei, Pierluigi},
  year = {2009},
  month = nov,
  journal = {Autonomous Robots},
  volume = {27},
  number = {4},
  pages = {353--371},
  issn = {0929-5593, 1573-7527},
  doi = {10.1007/s10514-009-9156-5},
  urldate = {2023-10-04},
  langid = {english}
}

Dataset corrections

Notice a specific issue after reviewing the page?

Report an inaccuracy